© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6980
    Prev
    Next
    INDEX
    Explanations

    answer questions

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences where the assistant asserts its role and safety/policy boundaries (self-description and refusal/explanation phrasing).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olio
    0.71
    hé
    0.65
    ल
    0.64
    тың
    0.61
    T
    0.60
    ن
    0.59
     But
    0.57
    kannya
    0.57
    Other
    0.57
     Other
    0.56
    POSITIVE LOGITS
    <unused2222>
    0.71
     помощью
    0.64
     medicamento
    0.64
     आदान
    0.61
     chatbots
    0.61
     utilizado
    0.60
     finalText
    0.59
     역할을
    0.59
     mediante
    0.59
     seul
    0.59
    Activations Density 4.229%

    No Known Activations